Happy to become a FISPE at #icpe2023 alongside my good friend Sallie Pearson!

It's cliche but I made a list of "what I expect from my students" a while ago and thought it may be helpful for folks here. A very long thread below:

We're thrilled to announce a special 4-part webinar series, "Advances in the Design and Analysis of Pragmatic Clinical Trials." Learn more and view the full schedule. #pctGR #pragmatictrials #biostatistics ➡️ bit.ly/45BYOZr

CAUSALab is looking forward to an exciting year ahead! We kicked off the year with a team social enjoying some food, drinks & karaoke. We've got a busy year ahead & we can't wait to share #research our team has been working on. Stay tuned for CAUSALab news and events!

Today is the 1st day of National Postdoc Appreciation Week #NPAW23. CAUSALab is so thankful for our amazing postdocs. Thank you for your dedication, hard work, and significant contributions to #publichealth research & discovery. We are lucky to have you all on the team!

How the methods for #HybridControl compare with each other in early phase (umbrella) trials? See my work with Roche in Pharmaceutical Statistics @PSIupdate onlinelibrary.wiley.com/doi/10.1002/ps…

Check out this article on Stats and Data Science Views statisticsviews.com/article/lay-ab…

Why Stating Hypotheses in Grant Applications Is Unnecessary 👀 New Viewpoint by Miguel Hernán Sander Greenland jamanetwork.com/journals/jama/…

We developed new methods to incorporate all possible structured prior knowledge into variable selection. Applications on the (latent) overlapping group Lasso for time-dependent Cox models and l_0 norm based penalized regression will be available soon.

Our new paper on JAMA delineates the current effect score analyses--how to use CATE to characterize HTE in RCTs. We are on our way to develop effect score analyses for survival outcomes and other settings. jamanetwork.com/journals/jama/…

New paper alert! CAUSALab researchers Guanbo Wang & Issa Dahabreh published “Using Effect Scores to Characterize Heterogeneity of Treatment Effects” alongside Patrick Heagerty of @uwbiostat in @JAMA. Read the article: jamanetwork.com/journals/jama/… #publichealth #effectscores #hsph

🧵 New Special Communication examines drawing causal inferences about the effects of interventions from observational studies in medical journals and suggests a framework that might be used. ja.ma/3UxeAjL

We also developed the method and efficient R package for the structured learning used in time-dependent Cox models. See our paper in Statistics in Medicine onlinelibrary.wiley.com/doi/10.1002/si… and R package 'sox' cran.r-project.org/web/packages/s…

Join us in congratulating PIs Dr. Dan Kramer BIDMC Smith Center & Dr. Issa Dahabreh CAUSALab on the award of their study RAPTOR-CIED from The Patient-Centered Outcomes Research Institute! Read more about the project here: bidmc.org/about-bidmc/ne… Harvard T.H. Chan School of Public Health

We developed methods to select effect modifiers and evaluate heterogeneity of treatment effects in longitudinal studies using structural nested models. Mireille Schnitzer Robert Platt IBS Biometrics Journal academic.oup.com/biometrics/art…

Looking for a more efficient way to estimate treatment effects in your randomized experiment? We introduce H-AIPW: a novel estimator that combines predictions from multiple foundation models with real experimental data. arxiv.org/abs/2502.04262

This is joint work with amazing collaborators: Javier Abad Martinez Guanbo Wang Konstantin Donhauser Ray Duch Fanny Yang and Issa Dahabreh. Code: github.com/jaabmar/HAIPW

(4/4) Postdoc Guanbo Wang is starting as Assistant Professor at the Dartmouth Institute for Health Policy & Clinical Practice. He will have a secondary appointment in the Department of Biomedical Data Science at the Geisel School of Medicine at Dartmouth.